@inproceedings{rubin-berant-2021-smbop-semi,
    title = "{S}m{B}o{P}: Semi-autoregressive Bottom-up Semantic Parsing",
    author = "Rubin, Ohad  and
      Berant, Jonathan",
    editor = "Kozareva, Zornitsa  and
      Ravi, Sujith  and
      Vlachos, Andreas  and
      Agrawal, Priyanka  and
      Martins, Andr{\'e}",
    booktitle = "Proceedings of the 5th Workshop on Structured Prediction for NLP (SPNLP 2021)",
    month = aug,
    year = "2021",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/icon-24-ingestion/2021.spnlp-1.2/",
    doi = "10.18653/v1/2021.spnlp-1.2",
    pages = "12--21",
    abstract = "The de-facto standard decoding method for semantic parsing in recent years has been to autoregressively decode the abstract syntax tree of the target program using a top-down depth-first traversal. In this work, we propose an alternative approach: a Semi-autoregressive Bottom-up Parser (SmBoP) that constructs at decoding step t the top-K sub-trees of height {\ensuremath{\leq}} t. Our parser enjoys several benefits compared to top-down autoregressive parsing. From an efficiency perspective, bottom-up parsing allows to decode all sub-trees of a certain height in parallel, leading to logarithmic runtime complexity rather than linear. From a modeling perspective, a bottom-up parser learns representations for meaningful semantic sub-programs at each step, rather than for semantically-vacuous partial trees. We apply SmBoP on Spider, a challenging zero-shot semantic parsing benchmark, and show that SmBoP leads to a 2.2x speed-up in decoding time and a {\textasciitilde}5x speed-up in training time, compared to a semantic parser that uses autoregressive decoding. SmBoP obtains 71.1 denotation accuracy on Spider, establishing a new state-of-the-art, and 69.5 exact match, comparable to the 69.6 exact match of the autoregressive RAT-SQL+Grappa."
}